daytonaio/daytona
Daytona is a secure and elastic infrastructure platform designed for safely running AI-generated code with high performance and scalability.
Awesome AI Agents › AI Application Development
langgenius/dify
Dify is an open-source platform designed for developing applications powered by large language models (LLMs). It offers an intuitive interface that integrates multiple advanced AI capabilities, enabling users to rapidly transition from prototyping to production deployment. The platform supports a visual workflow builder that allows users to create and test complex AI workflows easily. Dify provides comprehensive support for a wide range of LLMs, including proprietary, open-source, and self-hosted models such as GPT, Mistral, and Llama3, along with compatibility for any OpenAI API-compatible models. This extensive model support is facilitated through numerous inference providers. One of the standout features of Dify is its Prompt IDE, which offers an intuitive environment for crafting prompts, comparing model performances, and enhancing chat-based applications with features like text-to-speech. The platform also includes a robust Retrieval-Augmented Generation (RAG) pipeline that supports document ingestion and retrieval, with built-in capabilities for extracting text from common document formats like PDFs and PowerPoint presentations. Dify empowers users to define AI agents using LLM Function Calling or ReAct frameworks, supplemented by over 50 built-in tools such as Google Search, DALL·E, Stable Diffusion, and WolframAlpha, enhancing the agents' functionality. The platform incorporates LLMOps features for monitoring and analyzing application logs and performance, enabling continuous improvement of prompts, datasets, and models based on real-world production data. Additionally, Dify functions as a Backend-as-a-Service, providing APIs that facilitate seamless integration of its features into custom business logic. It supports deployment via Docker Compose and offers both cloud and self-hosted options. The platform is well-documented and supported by an active community, making it accessible for developers aiming to build sophisticated AI applications efficiently. Keywords: LLM app development, AI workflow, RAG pipeline, agent capabilities, model management, observability, Prompt IDE, document ingestion, text extraction, LLM Function Calling, ReAct, AI agents, LLMOps, Backend-as-a-Service, Docker, open-source, GPT, Mistral, Llama3, OpenAI API-compatible, AI application platform, self-hosting, cloud deployment, AI tools, AI integration, AI monitoring, AI performance analysis.
https://github.com/langgenius/dify
Also in AI Application Development
e2b-dev/awesome-ai-agents
A curated and comprehensive list of AI autonomous agents categorized into open-source and closed-source projects, serving as a valuable resource for exploring, building, and contributing to AI agent development.
mlflow/mlflow
MLflow is an open-source platform that manages the full machine learning lifecycle, providing tools for experiment tracking, model packaging, deployment, evaluation, and observability in one integrated solution.
pydantic/pydantic-ai
PydanticAI is a Python agent framework that simplifies building production-grade Generative AI applications by providing type-safe, structured, and model-agnostic integration with multiple LLMs, along with features like dependency injection and real-time debugging.
GoogleCloudPlatform/generative-ai
A comprehensive repository of sample code, notebooks, and resources for developing and managing generative AI workflows on Google Cloud using Gemini models on Vertex AI.
0xPlaygrounds/rig
Rig is a Rust library for building scalable, modular, and ergonomic fullstack agents powered by large language models, supporting multiple LLM providers and vector stores for AI integration.
mnfst/manifest
Manifest is an open-source components library built on shadcn/ui for creating customizable and production-ready UI components to develop ChatGPT and conversational AI applications efficiently.
purocean/yn
Yank Note is a highly extensible Markdown editor featuring AI assistance, version control, encryption, code execution, and rich multimedia embedding for enhanced productivity.